# AlphaEvolve: an AI improved a maths record from 1969

URL: https://ai-pulse.aglaganova.com/blog/alphaevolve-an-ai-improved-a-maths-record-from-1969
Published: 2026-10-09
Author: Roman Aglaganov, Full-stack developer
Category: Research
Region: Global
Tags: science, coding

> For 56 years, the best way to multiply two 4×4 complex matrices took 49 multiplications. Google DeepMind’s AlphaEvolve found one that takes 48. It sounds tiny. It is not.

![Typographic cover: 49 to 48, AI beat a 1969 record in matrix maths](https://ai-pulse.aglaganova.com/api/media/file/alphaevolve-1.png)

Multiplying matrices, grids of numbers, is the most important boring thing computers do. Graphics, physics simulations and every AI model run on it. So when someone finds a faster way to do it, mathematicians pay attention.

## Strassen’s trick

In 1969, the German mathematician Volker Strassen showed that the schoolbook method, which needs 64 multiplications to multiply two 4×4 matrices, was not the best possible. His clever rearrangement needed 49. For complex-valued matrices, the kind used in physics and signal processing, nobody beat that for 56 years.

## Enter AlphaEvolve

In May 2025, Google DeepMind announced AlphaEvolve, a coding agent that combines its Gemini language models with an evolutionary process. Gemini proposes changes to a program; an automatic evaluator scores each version; the best survive and get mutated again, round after round. It is natural selection, with code instead of finches.

Among its results, AlphaEvolve found a way to multiply two 4×4 complex matrices with 48 multiplications. One fewer than Strassen. Repeated billions of times inside larger calculations, one multiplication adds up.

## Not just matrices

DeepMind set AlphaEvolve loose on about 50 open maths problems. It matched the best known solutions in about 75% of cases and improved on them in about 20%, including progress on the kissing number problem, a 300-year-old puzzle about how many spheres can touch one sphere at the same time.

It also worked on Google’s own infrastructure: a scheduling rule it found for Google’s data centres has been in production for over a year and recovers, on average, 0.7% of Google’s worldwide computing resources. At Google’s scale, that is a lot of free computers.

**Why it matters:** language models are often accused of only remixing what they have seen. Paired with a strict automatic checker, they can find genuinely new things, and in maths a proof is a proof, whoever finds it.

## Sources

- [Google DeepMind: AlphaEvolve, a Gemini-powered coding agent for designing advanced algorithms](https://deepmind.google/discover/blog/alphaevolve-a-gemini-powered-coding-agent-for-designing-advanced-algorithms/)
- [Wikipedia: AlphaEvolve](https://en.wikipedia.org/wiki/AlphaEvolve)